Compression-based $k$NN for Class Incremental Continual Learning

Catastrophic forgetting is a key challenge in continual learning.In the adjoining field of stream machine learning, few methods target the related problem of re-occurring drift by avoiding forgetting old data.In this work, we investigate whether we can transfer such strategies from the stream machine learning to the continual learning setup.Based on our consideration, we propose a simple yet efficient compression-based kNN scheme and evaluate it experimentally.